atlas

Research map / 3D vision / NeRF and radiance fields

DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 5 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use DäRF with patch-wise fitting, MDE adaptation, and confidence modelingK-planes · ScanNet 9–10 viewsPSNR: 16.38 -> 18.29Helped
use DäRF with patch-wise fitting, MDE adaptation, and confidence modelingK-planes · ScanNet 18–20 viewsPSNR: 21.54 -> 21.58Helped
use DäRF with patch-wise fitting, MDE adaptation, and confidence modelingK-planes · Tanks and Temples 10 viewsPSNR: 14.12 -> 15.70Helped
add seen-view depth regularization (ablation)K-planes baseline · ScanNet ablationPSNR: 18.70 -> 19.71Helped
add unseen-view depth regularization (ablation)K-planes with seen-view depth regularization · ScanNet ablationPSNR: 19.71 -> 21.21Helped
add MDE adaptation (ablation)K-planes with seen- and unseen-view depth regularization · ScanNet ablationPSNR: 21.21 -> 21.39Helped
add confidence modeling (ablation)K-planes with MDE adaptation · ScanNet ablationPSNR: 21.39 -> 21.58Helped
use local instead of global scale-shift fitting (ablation)K-planes with seen-view MDE distillation · ScanNet local fitting ablationPSNR: 19.05 -> 19.71Helped
replace DPT with LeReS (ablation)DäRF · ScanNet MDE baseline ablationPSNR: 21.58 -> 21.31Hurt
replace DPT with MiDaS (ablation)DäRF · ScanNet MDE baseline ablationPSNR: 21.58 -> 21.48Hurt
use the scale-shift MDE adaptation loss alone instead of both adaptation terms (ablation)DäRF · ScanNet MDE adaptation ablationPSNR: 21.58 -> 21.31Hurt
use the L1 MDE adaptation loss alone instead of both adaptation terms (ablation)DäRF · ScanNet MDE adaptation ablationPSNR: 21.58 -> 21.48Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy